Analyzing Drum Patterns Using Conditional Deep Belief Networks

  title={Analyzing Drum Patterns Using Conditional Deep Belief Networks},
  author={Eric Battenberg and David Wessel},
We present a system for the high-level analysis of beatsynchronous drum patterns to be used as part of a comprehensive rhythmic understanding system. We use a multilayer neural network, which is greedily pre-trained layerby-layer using restriced Boltzmann machines (RBMs), in order to model the contextual time-sequence information of a drum pattern. For the input layer of the network, we use a conditional RBM, which has been shown to be an effective generative model of multi-dimensional… CONTINUE READING
Highly Cited
This paper has 39 citations. REVIEW CITATIONS

9 Figures & Tables



Citations per Year

Citation Velocity: 5

Averaging 5 citations per year over the last 3 years.

Learn more about how we calculate this metric in our FAQ.